Classification of electroencephalogram signal for the detection of epilepsy using Innovative Genetic Programming

Abstract

Epilepsy, sometimes called seizure disorder, is a neurological condition that justifies itself as a susceptibility to seizures. A seizure is a sudden burst of rhythmic discharges of electrical activity in the brain that causes an alteration in behaviour, sensation, or consciousness. It is essential to have a method for automatic detection of seizures, as these seizures are arbitrary and unpredictable. A profound study of the electroencephalogram (EEG) recordings is required for the accurate detection of these epileptic seizures. In this study, an Innovative Genetic Programming framework is proposed for classification of EEG signals into seizure and nonseizure. An empirical mode decomposition technique is used for the feature extraction followed by genetic programming for the classification. Moreover, a method for intron deletion, hybrid crossover, and mutation operation is proposed, which are responsible for the increase in classification accuracy and a decrease in time complexity. This suggests that the Innovative Genetic Programming classifier has a potential for accurately predicting the seizures in an EEG signal and hints on the possibility of building a real‐time seizure detection system.

Classification of cardiac disorders using 1D local ternary patterns based on pulse plethysmograph signals

“…This work adopts a data‐driven method called empirical mode decomposition (EMD) for de‐noising the raw PuPG sensor data. EMD is a widely used method in biomedical signal analysis (Aziz et al, 2020; Bhardwaj, Sakalle, Bhardwaj, & Tiwari, 2019; Khan et al, 2020; Khan et al, 2020). EMD performs a multi‐scale decomposition of non‐stationary and non‐linear signals.…”

Epileptic Seizure Diagnosis Using EEG Signals

“…In 1875, the English physician, Richard Canton, discovered electrical currents in the brain responsible for elliptic seizure [2]. According to the latest study, more than 2% of the population worldwide is affected from epilepsy where 85% of those live in developing countries and has adverse effects on their daily life and productivity [3].Epilepsy is a critical neurological brain disorder originating from temporary abnormal discharges of the brain electrical activity, leading to uncontrollable movements and trembling [4]. resulting in altered behaviors , such as losing consciousness, jerky movements, temporary loss of breath and memory loss [5].There are many injuries that can lead to epilepsy, the most important of which are (Genetic injury, head injury, brain tumor, birth trauma, ext …).…”

“…The general detection of epileptic activity requires manual scanning of EEG recordings, which commonly takes several days to complete [2]. Visual inspection for discriminating EEG signals is time-consuming, imprecise, and costly, especially in the case of long-term recordings [4]. CAD (computer-aided diagnosis) play an important role to develop robust and reliable techniques for epileptic activity detection in EEG signals [6].…”

“…CAD systems in medicine may use diagnostic rules to emulate the way a skilled human expert makes diagnostic decisions [7]. Nowadays, many researchers have used different techniques and methods such as using time-frequency analysis [8], naive bayes and K-NN classifiers [7], multidomain feature extraction and nonlinear analysis [3], a multi-context learning approach [12], logistic model trees [9], Innovative genetic programming [6], EEG signals [13], biomedical signals [4], deep learning approach [15], a computer aided analysis scheme [7], by which people with epilepsy are detected. These method are completely different from the way that has been used in the past, where epileptic seizures are diagnosed by clinical observation and recent changes recorded [8].…”

“…Distance from all training data to testing data is evaluated, candidate the point with the lowest distance is called the nearest neighbor. The K-NN algorithm structure are show in figure(4).…”